Prediction of Pelvic Organ Prolapse Postsurgical Outcome Using Biomaterial-Induced Blood Cytokine Levels: Machine Learning Approach.

BACKGROUND: Pelvic organ prolapse (POP) refers to symptomatic descent of the vaginal wall. To reduce surgical failure rates, surgical correction can be augmented with the insertion of polypropylene mesh. This benefit is offset by the risk of mesh complication, predominantly mesh exposure through the vaginal wall. If mesh placement is under consideration as part of prolapse repair, patient selection and counseling would benefit from the prediction of mesh exposure; yet, no such reliable preoperative method currently exists. Past studies indicate that inflammation and associated cytokine release is correlated with mesh complication. While some degree of mesh-induced cytokine response accompanies implantation, excessive or persistent cytokine responses may elicit inflammation and implant rejection. OBJECTIVE: Here, we explore the levels of biomaterial-induced blood cytokines from patients who have undergone POP repair surgery to (1) identify correlations among cytokine expression and (2) predict postsurgical mesh exposure through the vaginal wall. METHODS: Blood samples from 20 female patients who previously underwent surgical intervention with transvaginal placement of polypropylene mesh to correct POP were collected for the study. These included 10 who experienced postsurgical mesh exposure through the vaginal wall and 10 who did not. Blood samples incubated with inflammatory agent lipopolysaccharide, with sterile polypropylene mesh, or alone were analyzed for plasma levels of 13 proinflammatory and anti-inflammatory cytokines using multiplex assay. Data were analyzed by principal component analysis (PCA) to uncover associations among cytokines and identify cytokine patterns that correlate with postsurgical mesh exposure through the vaginal wall. Supervised machine learning models were created to predict the presence or absence of mesh exposure and probe the number of cytokine measurements required for effective predictions. RESULTS: PCA revealed that proinflammatory cytokines interferon gamma, interleukin 12p70, and interleukin 2 are the largest contributors to the variance explained in PC 1, while anti-inflammatory cytokines interleukins 10, 4, and 6 are the largest contributors to the variance explained in PC 2. Additionally, PCA distinguished cytokine correlations that implicate prospective therapies to improve postsurgical outcomes. Among machine learning models trained with all 13 cytokines, the artificial neural network, the highest performing model, predicted POP surgical outcomes with 83% (15/18) accuracy; the same model predicted POP surgical outcomes with 78% (14/18) accuracy when trained with just 7 cytokines, demonstrating retention of predictive capability using a smaller cytokine group. CONCLUSIONS: This preliminary study, incorporating a sample size of just 20 participants, identified correlations among cytokines and demonstrated the potential of this novel approach to predict mesh exposure through the vaginal wall following transvaginal POP repair surgery. Further study with a larger sample size will be pursued to confirm these results. If corroborated, this method could provide a personalized medicine approach to assist surgeons in their recommendation of POP repair surgeries with minimal potential for adverse outcomes.

Designing and executing a functional exercise to test a novel informatics tool for mass casualty triage.

OBJECTIVE: The testing of informatics tools designed for use during mass casualty incidents presents a unique problem as there is no readily available population of victims or identical exposure setting. The purpose of this article is to describe the process of designing, planning, and executing a functional exercise to accomplish the research objective of validating an informatics tool specifically designed to identify and triage victims of irritant gas syndrome agents. MATERIALS AND METHODS: During a 3-year time frame, the research team and partners developed the Emergency Department Informatics Computational Tool and planned a functional exercise to test it using medical records data from 298 patients seen in 1 emergency department following a chlorine gas exposure in 2005. RESULTS: The research team learned valuable lessons throughout the planning process that will assist future researchers with developing a functional exercise to test informatics tools. Key considerations for a functional exercise include contributors, venue, and information technology needs (ie, hardware, software, and data collection methods). DISCUSSION: Due to the nature of mass casualty incidents, testing informatics tools and technology for these incidents is challenging. Previous studies have shown a functional exercise as a viable option to test informatics tools developed for use during mass casualty incidents. CONCLUSION: Utilizing a functional exercise to test new mass casualty management technology and informatics tools involves a painstaking and complex planning process; however, it does allow researchers to address issues inherent in studying informatics tools for mas casualty incidents.

Mobile Decision Support Tool for Emergency Departments and Mass Casualty Incidents (EDIT): Initial Study.

BACKGROUND: Chemical exposures pose a significant threat to life. A rapid assessment by first responders and emergency nurses is required to reduce death and disability. Currently, no informatics tools exist to process victims of chemical exposures efficiently. The surge of patients into a hospital emergency department during a mass casualty incident creates additional stress on an already overburdened system, potentially placing patients at risk and challenging staff to process patients for appropriate care and treatment efficacy. Traditional emergency department triage models are oversimplified during highly stressed mass casualty incident scenarios in which there is little margin for error. Emerging mobile technology could alleviate the burden placed on nurses by allowing the freedom to move about the emergency department and stay connected to a decision support system. OBJECTIVE: This study aims to present and evaluate a new mobile tool for assisting emergency department personnel in patient management and triage during a chemical mass casualty incident. METHODS: Over 500 volunteer nurses, students, and first responders were recruited for a study involving a simulated chemical mass casualty incident. During the exercise, a mobile application was used to collect patient data through a kiosk system. Nurses also received tablets where they could review patient information and choose recommendations from a decision support system. Data collected was analyzed on the efficiency of the app to obtain patient data and on nurse agreement with the decision support system. RESULTS: Of the 296 participants, 96.3% (288/296) of the patients completed the kiosk system with an average time of 3 minutes, 22 seconds. Average time to complete the entire triage process was 5 minutes, 34 seconds. Analysis of the data also showed strong agreement among nurses regarding the app's decision support system. Overall, nurses agreed with the system 91.6% (262/286) of the time when it came to choose an exposure level and 84.3% (241/286) of the time when selecting an action. CONCLUSIONS: The app reliably demonstrated the ability to collect patient data through a self-service kiosk system thus reducing the burden on hospital resources. Also, the mobile technology allowed nurses the freedom to triage patients on the go while staying connected to a decision support system in which they felt would give reliable recommendations.

An AI model for Rapid and Accurate Identification of Chemical Agents in Mass Casualty Incidents.

In this report we examine the effectiveness of WISER in identification of a chemical culprit during a chemical based Mass Casualty Incident (MCI). We also evaluate and compare Binary Decision Tree (BDT) and Artificial Neural Networks (ANN) using the same experimental conditions as WISER. The reverse engineered set of Signs/Symptoms from the WISER application was used as the training set and 31,100 simulated patient records were used as the testing set. Three sets of simulated patient records were generated by 5%, 10% and 15% perturbation of the Signs/Symptoms of each chemical record. While all three methods achieved a 100% training accuracy, WISER, BDT and ANN produced performances in the range of: 1.8%-0%, 65%-26%, 67%-21% respectively. A preliminary investigation of dimensional reduction using ANN illustrated a dimensional collapse from 79 variables to 40 with little loss of classification performance.

An Improved-Efficiency Compact Lamp for the Thermal Infrared.

A major type of infrared camera is sensitive to wavelengths in the 8-14 µm band and is mainly used for thermal imaging. Such cameras can also be used for general broadband infrared reflectance imaging when provided with a suitable light source. We report the design and properties of an infrared lamp using a heated alumina emitter suitable for active thermal infrared imaging, as well as comparisons to existing commercial light sources for this purpose. We find that the alumina lamp is a broadband non-blackbody source with a lower out-of-band emission intensity and therefore higher electrical efficiency for this application than existing commercial sources.

Chemical contrast observed in thermal images of blood-stained fabrics exposed to steam.

Thermal imaging is not ordinarily a good way to visualize chemical contrast. In recent work, however, we observed strong and reproducible images with chemical contrasts on blood-stained fabrics, especially on more hydrophobic fabrics like acrylic and polyester.